---
type: "post"
id: "get-started-with-llm-training-on-modal-c92ce5"
slug: "get-started-with-llm-training-on-modal-c92ce5"
title: "Get started with LLM training on Modal"
description: "Modal has released Modal Dojo, a library for LLM post-training and reinforcement learning."
retrieval_nugget: "Modal has released Modal Dojo, a library for LLM post-training and reinforcement learning."
published_at: "2026-10-22"
updated_at: "2026-10-22"
record_date: "2026-10-22"
date_kind: "published_at"
topics: ["models","ai-infrastructure","compute"]
entities: ["Modal","Modal Dojo","Hugging Face","Harbor","Miles","Slime"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Modal introduces a guide to getting started with LLM reinforcement-learning training on its platform, extending the archive’s coverage of RL post-training tools."
prior_refs: ["memory:991d73f0-7a41-8ab1-ae6f-adbf5c46b25a","memory:852d4b1b-4088-8546-adfc-7c802fafc1f7"]
source_url: "https://modal.com/blog/get-started-with-llm-training-on-modal"
source_urls: ["https://modal.com/blog/get-started-with-llm-training-on-modal"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:get-started-with-llm-training-on-modal-c92ce5"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/get-started-with-llm-training-on-modal-c92ce5/","markdown":"https://newruntime.com/posts/get-started-with-llm-training-on-modal-c92ce5.md","json":"https://newruntime.com/posts/get-started-with-llm-training-on-modal-c92ce5.json"}
---

# Get started with LLM training on Modal

## Retrieval answer

Modal has released Modal Dojo, a library for LLM post-training and reinforcement learning.

Modal has released Modal Dojo, a library for LLM post-training and reinforcement learning. Modal describes it as a package of training building blocks, tuned defaults, and observability tooling; the company says it is available now.

The library accepts a model, dataset, and training recipe. Modal says datasets can come from Hugging Face, Harbor environments, or a team's harness and evaluation data. Recipes specify hardware, parallelism, rollout volume, environments, and other training parameters. Modal says its recipes have been validated from 0.5-billion-parameter models to multi-trillion-parameter models, with support for user-supplied models.

Dojo includes a dashboard for loss and reward curves, framework metrics, rollout trajectories, substep profiling, and container logs. Its CLI can return a run's status, metadata, logs, and agent traces. The source does not provide independent benchmarks, pricing, or reproducible evidence for its claims about training performance or customer results.

Source: https://modal.com/blog/get-started-with-llm-training-on-modal

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- topic hub: [Ai Infrastructure](https://newruntime.com/topics/ai-infrastructure.md): Explore the ai-infrastructure topic hub.
- topic hub: [Compute](https://newruntime.com/topics/compute.md): Explore the compute topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)